Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already signal mutation (readOnlyHint=false) and non-idempotency, and the description adds meaningful behavioral context: the result is a saved, reusable draft; the draft is the only mutable surface; and the creation modes have mutually exclusive semantics. This goes beyond what annotations alone convey, though it does not describe response details—which is acceptable given an output schema exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences carry all essential information with no filler. The core purpose is front-loaded, and each sentence adds a distinct layer: what is created, how to start, and what happens next in the lifecycle.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 5-parameter tool with nested objects and an output schema, the description covers the creation workflow, parameter relationships, documentation prerequisite, and downstream lifecycle. Combined with the fully described schema, nothing needed to invoke it correctly seems missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds relationship semantics not present in the schema: config and cloneSplitterId are mutually exclusive and name alone creates an empty draft. It also restates the critical config constraint (must include a type: "other" entry) in prose, reinforcing the schema without fully duplicating it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Create a saved, reusable splitter (split group)', which clearly distinguishes it from sibling creation tools like create_classifier or create_extractor. The lifecycle references to update_splitter, publish_splitter_version, and split_document further anchor its unique role.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly explains the two starting modes (config vs cloneSplitterId) and that they are mutually exclusive, plus the fallback of name-only creating an empty draft. It also directs the agent to call get_documentation before hand-authoring config and names the exact downstream tools for editing, publishing, and running the splitter.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.